AI and AgentsOpenHandsPWSoftware development, agents, bug fixing, project management
OpenHands
An AI-driven software development agent that can write code, fix bugs, and manage projects
6781
View repositoryIndependent Column
Open-source projects worth exploring
Runnable, documented projects worth studying and extending.
AI and AgentsOpenHandsPW
Efficiency toolsManimPWMathematical animation, teaching, Python, 3B1B
Manim
3Blue1Brown uses a Python engine for creating mathematical animations, which can be AI-assisted in generating teaching animations
6780
View repositoryAI and AgentsMiroFishPWSwarm intelligence, prediction, Python, open source
MiroFish
A simple and universal swarm intelligence engine that can predict everything. Based on swarm intelligence algorithms implemented in Python, GitHub today has 2200+ stars
6685
View repository
AI and AgentsPage AgentPWagent, browser-automation, alibaba
Page Agent
Alibaba's open-source GUI agent for web pages, using natural language to control the web interface, supporting intelligent in-page operations, and today's GitHub trending 1200+ stars
6684
View repositoryEfficiency toolsDoclingPWDocument parsing, PDF, Markdown, IBM
Docling
IBM's open-source document parsing tool converts PDF, DOCX, etc. to Markdown, supporting tables and formulas
6688
View repository
Efficiency toolsDimensionX is a framework that can generate controllable 3D4D scenes from a single image. It can precisely control the generation process and generate a 360-degree panoramic viewPW3D/4D generation models
DimensionX is a framework that can generate controllable 3D4D scenes from a single image. It can precisely control the generation process and generate a 360-degree panoramic view
DimensionX is a framework that can generate controllable 3D4D scenes from a single image, supporting a 360-degree panoramic view and multiple camera control modes. ST-Director enables precise control over the spatial and temporal dimensions of video generation, enabling the creation of coherent multi-angle video sequences while maintaining scene consistency and supporting spatiotemporal variation
6679
View repositoryEfficiency toolsThe clawdbot-skills library covering 30+ common scenarios: awesome-clawdbot-skillsPWskills
The clawdbot-skills library covering 30+ common scenarios: awesome-clawdbot-skills
The clawdbot-skills library offers skills for over 30 commonly used scenarios, covering front-end development, DevOps, automation, financial management, health, smart home, and more, allowing users to find ready-made solutions here
6678
View repositoryOthersSegment Anything 2PWMeta, image segmentation, video segmentation, zero-shot
Segment Anything 2
Meta's universal image and video segmentation model allows zero-shot segmentation of any object
6682
View repository
Efficiency toolsPikaPWVideo generation, text-to-video, image-to-video, short video
Pika
AI video generation tool that converts text and images into high-quality short videos
6678
View repositoryOthersBarkPWAudio generation, TTS, music, Suno
Bark
Suno's open-source text-to-audio model supports speech, music, background sound effects, and non-verbal sounds
6581
View repositoryOthersPage AgentPWgui-agent, web-automation, alibaba, natural-language
Page Agent
Alibaba's open-source GUI agent for web pages uses natural language to control the web interface. No browser plugins, screenshots, or multimodal models are needed—pure JavaScript implementation, and a single line of code can be integrated into any web application, making it ideal for building AI Copilot and smart form filling.
6584
View repository
OthersLangChainPWLLM, RAG, Agent, Python
LangChain
Building a powerful framework for LLM applications, providing core capabilities such as chained calls, agents, and RAG, it is the preferred tool for AI application development
6586
View repositoryAI and AgentsMiroFishPWmulti-agent, prediction, simulation, swarm-intelligence
MiroFish
Based on multi-agent technology, the swarm intelligence prediction engine builds a high-fidelity parallel digital world, enabling thousands of agents with independent personalities and long-term memory to freely interact and evolve socially, precisely predicting future trends. Supports scenarios such as financial forecasting, public opinion analysis, and novel simulation.
6579
View repositoryEfficiency toolsA super popular AI short drama automatic generation tool these past two days: Huobao Drama, automates the entire process of script, characters, storyboarding, and video synthesisPWVideo generation, AI
A super popular AI short drama automatic generation tool these past two days: Huobao Drama, automates the entire process of script, characters, storyboarding, and video synthesis
Huobao Drama is a popular AI automatic short drama generation tool that automates the entire process from creative conception to final video production. It makes short drama production efficient; one person per computer can complete it in one hour, making it ideal for quickly validating concepts and producing customized short dramas, especially excelling in trending topics
6577
View repositoryOthersOpenRAGPWRAG, knowledge base, retrieval enhancement, LangFlow
OpenRAG
A one-stop RAG platform built on Langflow, Docling, and OpenSearch, offering comprehensive retrieval-enhanced generation capabilities with a single package deployment.
6580
View repositoryOthersDeep AgentsPWagent, langchain, python, ai
Deep Agents
LangChain's Agent framework, ready to use right out of the box. Built-in planning, file system, shell, and sub-agent capabilities, supporting MCP protocol extensions.
6586
View repositoryEfficiency toolsCodex CLIPWOpenAI, terminal, agent, command line
Codex CLI
OpenAI's terminal programming agent writes and runs code in natural language within the command line
6578
View repositoryOthersPageAgentPWGUI Agent, web automation, Alibaba, Copilot
PageAgent
Alibaba's open-source GUI Agent for web pages controls the web interface using natural language, requiring no browser extensions or screenshots, fully JS implementation, and can quickly integrate AI Copilot into products
6577
View repositoryEfficiency toolsLiteLLMPWAPI proxy, multi-model, unified interface, OpenAI
LiteLLM
A unified LLM API proxy that calls 100+ types of LLMs in OpenAI format, including Azure, Anthropic, Ollama, and others
6577
View repositoryOthersSmolagentsPWHuggingFace, lightweight, Agent, tool call
Smolagents
HuggingFace's open-source lightweight agent library, simple API build tool for calling agents
6479
View repositoryOthersPhidataPWAI assistant, memory, knowledge base, tool calls
Phidata
Build an AI assistant framework with memory, knowledge, and tools, supporting multimodal and multi-agent capabilities
6481
View repositoryOthersMistralPWMistral: efficient, small parameters, strong performance
Mistral
Mistral AI is an open-source, efficient large language model series that delivers powerful performance with small parameters
6479
View repository
OthersLlama 3PWMeta, Llama, open source, multilingual
Llama 3
Meta's open-source third-generation Llama model, available in 8B and 70B versions, supports multiple languages
6487
View repository
Efficiency toolsAn AI web browsing automation tool: Stagehand, which can help you perform clicking, typing, searching, and other operations on web pages, with natural language interactionPWOpen source, AI
An AI web browsing automation tool: Stagehand, which can help you perform clicking, typing, searching, and other operations on web pages, with natural language interaction
Stagehand is an AI web browsing automation tool that supports clicking, typing, searching, and other operations, and can interact through natural language. It features visual recognition capabilities, can analyze web page structures, extract structured data, perform automated testing, and record operation logs, while also being lightweight and configurable
6481
View repository